© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 12449
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining, discussing, or exploring various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    discussions involving significant topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.74
    ibi
    -0.72
    iple
    -0.72
    ahu
    -0.71
    iless
    -0.66
    rament
    -0.66
    ¬¼
    -0.66
    ega
    -0.65
    endo
    -0.65
    olo
    -0.63
    POSITIVE LOGITS
     namely
    1.19
     including
    1.08
     culminating
    1.00
     which
    0.97
     particularly
    0.91
     noting
    0.90
    particularly
    0.90
     wherein
    0.88
     especially
    0.86
     concluding
    0.84
    Activations Density 0.433%

    No Known Activations